Pub Date : 2022-12-31DOI: 10.55579/jaec.202264.386
T. N. Nguyen, P. Fazio, M. Voznák
This paper studies a decode-and-forward (DF) full-duplex cooperative relaying network, whereas one transmitter S transmits information to one receiver D via the help of a relay R. In particular, the transmitter can simultaneously transmit energy and information (SWIPT) to relay R using time-switching (TS) method. Then, relay R can utilize the harvested energy to transfer information to the receiver D. Based on the proposed system model, we derive the mathematical expressions for the system capacity for the proposed non-adaptive TS (NATSP) and adaptive TS protocols (ATSP). Next, the Monte Carlo simulations are executed to corroborate the exactness of the analysis compared to the numerical results. Both numerical and analytical results show the superiority of ATSP over NATSP.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.
{"title":"Capacity Maximizing Adaptive Time-Switching Protocol for Energy Harvesting Full-Duplex Relaying Network over Rayleigh Fading Channel","authors":"T. N. Nguyen, P. Fazio, M. Voznák","doi":"10.55579/jaec.202264.386","DOIUrl":"https://doi.org/10.55579/jaec.202264.386","url":null,"abstract":"This paper studies a decode-and-forward (DF) full-duplex cooperative relaying network, whereas one transmitter S transmits information to one receiver D via the help of a relay R. In particular, the transmitter can simultaneously transmit energy and information (SWIPT) to relay R using time-switching (TS) method. Then, relay R can utilize the harvested energy to transfer information to the receiver D. Based on the proposed system model, we derive the mathematical expressions for the system capacity for the proposed non-adaptive TS (NATSP) and adaptive TS protocols (ATSP). Next, the Monte Carlo simulations are executed to corroborate the exactness of the analysis compared to the numerical results. Both numerical and analytical results show the superiority of ATSP over NATSP.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.","PeriodicalId":250655,"journal":{"name":"J. Adv. Eng. Comput.","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127000653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-31DOI: 10.55579/jaec.202264.380
Willy Stephen Tounsi Fokui, L. Ngoo, Michael Juma Saulo
This paper proposes a method of optimally utilizing electric vehicles (EVs) in the distribution network. The method is firstly based on segregating the distribution network into communities and then optimally placing an EV charging station (EVCS) in each community using the backward forward sweep (BFS) technique. The Second phase uses particle swarm optimization (PSO) to size and allocates photovoltaic systems in the network for power loss minimization and voltage improvement. The proposed method is tested on an IEEE 33 node test feeder and simulation results showed the effectiveness of the BFS in finding the best nodes for the placement of EVCS in each community as well as the effectiveness of the PSO in allocating the photovoltaic systems. To validate the effectiveness of the BFS technique, its results obtained are compared with those obtained when the EVCSs are placed on some nodes other than those chosen by the BFS technique.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.
{"title":"Optimal Integration of Electric Vehicle Charging Stations and Compensating Photovoltaic Systems in a Distribution Network Segregated into Communities","authors":"Willy Stephen Tounsi Fokui, L. Ngoo, Michael Juma Saulo","doi":"10.55579/jaec.202264.380","DOIUrl":"https://doi.org/10.55579/jaec.202264.380","url":null,"abstract":"This paper proposes a method of optimally utilizing electric vehicles (EVs) in the distribution network. The method is firstly based on segregating the distribution network into communities and then optimally placing an EV charging station (EVCS) in each community using the backward forward sweep (BFS) technique. The Second phase uses particle swarm optimization (PSO) to size and allocates photovoltaic systems in the network for power loss minimization and voltage improvement. The proposed method is tested on an IEEE 33 node test feeder and simulation results showed the effectiveness of the BFS in finding the best nodes for the placement of EVCS in each community as well as the effectiveness of the PSO in allocating the photovoltaic systems. To validate the effectiveness of the BFS technique, its results obtained are compared with those obtained when the EVCSs are placed on some nodes other than those chosen by the BFS technique.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.","PeriodicalId":250655,"journal":{"name":"J. Adv. Eng. Comput.","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128541038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-31DOI: 10.55579/jaec.202264.370
M. Ali, D. Kumar
Face recognition has aroused great interest in a range of industries due to its practical applications nowadays. It is a biometric method that is used to identify and certify people with unique biological traits in a reliable and timely manner. Although iris and fingerprint recognition technologies are more accurate, face recognition technology is the most common and frequently utilized since it is simple to deploy and execute and does not require any physical input from the user. This study compares Neural Networks using (SGD, Adam, or L-BFGS-B) optimizers, with different activation functions (Sigmoid, Tanh, or ReLU), and deep learning feature extraction methodologies including Squeeze Net, VGG19, or Inception model. The inception model outperforms the Squeeze Net and VGG19 in terms of accuracy. Based on the findings of the inception model, we achieved 93.6% of accuracy in a neural network with four layers and forty neurons by utilizing the SGD optimizer with the ReLU activation function. We also noticed that using the ReLU activation function with any of the three optimizers achieved the best results based on findings of the inception model, as it achieved 93.6%, 89.1%, and 94% of accuracy for each of the optimization algorithms SGD, Adam, and BFGS, respectively.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.
{"title":"The Impact of Optimization Algorithms on The Performance of Face Recognition Neural Networks","authors":"M. Ali, D. Kumar","doi":"10.55579/jaec.202264.370","DOIUrl":"https://doi.org/10.55579/jaec.202264.370","url":null,"abstract":"Face recognition has aroused great interest in a range of industries due to its practical applications nowadays. It is a biometric method that is used to identify and certify people with unique biological traits in a reliable and timely manner. Although iris and fingerprint recognition technologies are more accurate, face recognition technology is the most common and frequently utilized since it is simple to deploy and execute and does not require any physical input from the user. This study compares Neural Networks using (SGD, Adam, or L-BFGS-B) optimizers, with different activation functions (Sigmoid, Tanh, or ReLU), and deep learning feature extraction methodologies including Squeeze Net, VGG19, or Inception model. The inception model outperforms the Squeeze Net and VGG19 in terms of accuracy. Based on the findings of the inception model, we achieved 93.6% of accuracy in a neural network with four layers and forty neurons by utilizing the SGD optimizer with the ReLU activation function. We also noticed that using the ReLU activation function with any of the three optimizers achieved the best results based on findings of the inception model, as it achieved 93.6%, 89.1%, and 94% of accuracy for each of the optimization algorithms SGD, Adam, and BFGS, respectively.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.","PeriodicalId":250655,"journal":{"name":"J. Adv. Eng. Comput.","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124709176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-31DOI: 10.55579/jaec.202264.383
S. A. Bhanotar
This article introduces some important sequences and their connection with the hypotenuse of the Fermat family triangle with the NSW, Jha, and Pell sequences. Defining an exciting fact about the sequence, {3; 17; 99; 577; ...}, which consists of the first leg, has a corresponding second leg is an even perfect square such that the triple will be Pythagorean triple. Moreover, it shows the relation between Jha and NSW sequences.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.
{"title":"On Some Important Sequences and Their Relation with Pythagorean - Fermat Triples","authors":"S. A. Bhanotar","doi":"10.55579/jaec.202264.383","DOIUrl":"https://doi.org/10.55579/jaec.202264.383","url":null,"abstract":"This article introduces some important sequences and their connection with the hypotenuse of the Fermat family triangle with the NSW, Jha, and Pell sequences. Defining an exciting fact about the sequence, {3; 17; 99; 577; ...}, which consists of the first leg, has a corresponding second leg is an even perfect square such that the triple will be Pythagorean triple. Moreover, it shows the relation between Jha and NSW sequences.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.","PeriodicalId":250655,"journal":{"name":"J. Adv. Eng. Comput.","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116862445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-31DOI: 10.55579/jaec.202264.393
Pham Tan Hung, P. Phuc
In this article, a free vibration analysis of the functionally graded porous piezoelectric (FGPP) microplates is firstly solved by using a combination of two variable refined plate theory (RPT), modified strain gradient theory (MSGT) and isogeometric analysis (IGA). The FGPP microplate is composed of piezoelectric material with pores, which are distributed across the plate thickness in uniform and non-uniform distributions. The modified strain gradient theory is used to capture the size effect on the natural frequency of the FGPP microplates. According to the variational principle of RPT with two variables, the governing equations are derived and solved by the IGA. The influence of the length scale parameters (LSPs), external electric voltage, power law index, length-to-thickness ratio, aspect ratio and boundary conditions (BCs) on the natural frequency of the FGPP microplates is studied. The numerical results show that a rise in the porosity coefficient makes a decrease in the microplate’s stiffness, while an increase in LSPs leads to a rise in the microplate’s stiffness.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.
{"title":"A Two Variable Refined Plate Theory for Isogeometric Vibration Analysis of The Functionally Graded Piezoelectric Microplates with Porosities","authors":"Pham Tan Hung, P. Phuc","doi":"10.55579/jaec.202264.393","DOIUrl":"https://doi.org/10.55579/jaec.202264.393","url":null,"abstract":"In this article, a free vibration analysis of the functionally graded porous piezoelectric (FGPP) microplates is firstly solved by using a combination of two variable refined plate theory (RPT), modified strain gradient theory (MSGT) and isogeometric analysis (IGA). The FGPP microplate is composed of piezoelectric material with pores, which are distributed across the plate thickness in uniform and non-uniform distributions. The modified strain gradient theory is used to capture the size effect on the natural frequency of the FGPP microplates. According to the variational principle of RPT with two variables, the governing equations are derived and solved by the IGA. The influence of the length scale parameters (LSPs), external electric voltage, power law index, length-to-thickness ratio, aspect ratio and boundary conditions (BCs) on the natural frequency of the FGPP microplates is studied. The numerical results show that a rise in the porosity coefficient makes a decrease in the microplate’s stiffness, while an increase in LSPs leads to a rise in the microplate’s stiffness.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.","PeriodicalId":250655,"journal":{"name":"J. Adv. Eng. Comput.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115401603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-30DOI: 10.55579/jaec.202263.367
Quang Dung Nguyen, Hoang Trung Le, Hoang Thien Le, Viet Hung Tran
Flooding is one of the most common natural disasters in Vietnam. Although a hydrological monitoring system has been developed in Vietnam, the adoption of a Flood Warning and Monitoring System (FWMS) is still limited. A practical issue is that the river water levels is rarely flat, but undulating with flood water ripples, which makes the measurement inaccurate. In this paper, we will design a recursive Kalman estimation for fluctuating flood water level in the Node-Red IoT network. Indeed, the low complexity of the popular Kalman filter algorithm is very suitable for a low-cost IoT system like Node-Red. In our experiments, the accuracy of our Kalman algorithm is far superior to the standard Moving Average (MA) algorithm. To our knowledge, this is the first time that the Kalman filter has been used in a practical Node-Red IoT experiment. We will show that our novel Moving-update Kalman algorithm, which combines MA and Kalman methods, can track data recursively without prior knowledge of noise’s variance. Our novel algorithm is of linear complexity and, hence, fast enough for low cost IoT and FWMS systems in developing countries like Vietnam. We also included the industrial Message Queuing Telemetry Transport (MQTT) protocol in IoT network in our Node-Red system, which means our designed Node-Red proposal is capable of transferring data to any FWMS network via internet. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.
{"title":"Moving-update Kalman Algorithm in Low-cost Node-Red IoT Network for Estimating Flood Water Level","authors":"Quang Dung Nguyen, Hoang Trung Le, Hoang Thien Le, Viet Hung Tran","doi":"10.55579/jaec.202263.367","DOIUrl":"https://doi.org/10.55579/jaec.202263.367","url":null,"abstract":"Flooding is one of the most common natural disasters in Vietnam. Although a hydrological monitoring system has been developed in Vietnam, the adoption of a Flood Warning and Monitoring System (FWMS) is still limited. A practical issue is that the river water levels is rarely flat, but undulating with flood water ripples, which makes the measurement inaccurate. In this paper, we will design a recursive Kalman estimation for fluctuating flood water level in the Node-Red IoT network. Indeed, the low complexity of the popular Kalman filter algorithm is very suitable for a low-cost IoT system like Node-Red. In our experiments, the accuracy of our Kalman algorithm is far superior to the standard Moving Average (MA) algorithm. To our knowledge, this is the first time that the Kalman filter has been used in a practical Node-Red IoT experiment. We will show that our novel Moving-update Kalman algorithm, which combines MA and Kalman methods, can track data recursively without prior knowledge of noise’s variance. Our novel algorithm is of linear complexity and, hence, fast enough for low cost IoT and FWMS systems in developing countries like Vietnam. We also included the industrial Message Queuing Telemetry Transport (MQTT) protocol in IoT network in our Node-Red system, which means our designed Node-Red proposal is capable of transferring data to any FWMS network via internet. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.","PeriodicalId":250655,"journal":{"name":"J. Adv. Eng. Comput.","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125588610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-30DOI: 10.55579/jaec.202263.378
I. A. Fetuga, O. T. Olakoyejo, A. S. Shote, Gbeminiyi Mike Sobamowo, O. Oluwatusin, J. K. Gbegudu
This current work mainly focuses on the enhancement of the heat transfer and fluid flow characteristics of shell-and-tube heat exchangers by incorporating dimples on the smooth or conventional tubes. With the aid of the ANSYS (Fluent) commercial software package, Computational Fluid Dynamics (CFD) simulations under a steady-state condition were conducted on heat exchanger having a single shell and 12 tubes (with or without dimples), 50% baffle cut, 100mm baffle spacing and turbulent flow. The temperature, velocity, and pressure fields at the shell and tube zone in both cases are analyzed. The computational fluid dynamics results of the heat exchanger with dimpled tubes are compared with conventional (smooth) tubes. However, the results show that a shell and tube heat exchanger with dimpled tubes has a higher overall heat transfer coefficient than that of conventional (smooth) tubes. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.
{"title":"Thermal and Fluid Flow Analysis of Shell-and-Tube Heat Exchangers with Smooth and Dimpled Tubes","authors":"I. A. Fetuga, O. T. Olakoyejo, A. S. Shote, Gbeminiyi Mike Sobamowo, O. Oluwatusin, J. K. Gbegudu","doi":"10.55579/jaec.202263.378","DOIUrl":"https://doi.org/10.55579/jaec.202263.378","url":null,"abstract":"This current work mainly focuses on the enhancement of the heat transfer and fluid flow characteristics of shell-and-tube heat exchangers by incorporating dimples on the smooth or conventional tubes. With the aid of the ANSYS (Fluent) commercial software package, Computational Fluid Dynamics (CFD) simulations under a steady-state condition were conducted on heat exchanger having a single shell and 12 tubes (with or without dimples), 50% baffle cut, 100mm baffle spacing and turbulent flow. The temperature, velocity, and pressure fields at the shell and tube zone in both cases are analyzed. The computational fluid dynamics results of the heat exchanger with dimpled tubes are compared with conventional (smooth) tubes. However, the results show that a shell and tube heat exchanger with dimpled tubes has a higher overall heat transfer coefficient than that of conventional (smooth) tubes. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.","PeriodicalId":250655,"journal":{"name":"J. Adv. Eng. Comput.","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126175374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-30DOI: 10.55579/jaec.202263.375
Q. Pham, D. Nguyen
Springback prediction is one of the most challenging in finite element analysis for sheet metal forming processes. The demand requests the development of a kinematic hardening model and parameter identification. This study presents a schematic strategy to identify parameters of Chaboche’s kinematic hardening model based on a differential evolution optimization method. To this goal, several tension-compression (TC) tests were conducted to observe the Bauchinger’s effects and kinematic hardening behaviors of two aluminum alloy sheets: AA6022-T6 and AA7075-T76. A Python code is developed to apply the proposed method in identifying parameters of the kinematic hardening model. The calibrated material models were implemented in Abaqus software to simulate V-bending and U-bending tests for the investigated materials. The predictions for springback amount match well with the experimental measurements, which verifies the effectiveness of the presented identificationstrategy.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.
{"title":"Parameter Identification of Chaboche Model for Aluminum Alloy Sheets Based on Differential Evolution Algorithm","authors":"Q. Pham, D. Nguyen","doi":"10.55579/jaec.202263.375","DOIUrl":"https://doi.org/10.55579/jaec.202263.375","url":null,"abstract":"Springback prediction is one of the most challenging in finite element analysis for sheet metal forming processes. The demand requests the development of a kinematic hardening model and parameter identification. This study presents a schematic strategy to identify parameters of Chaboche’s kinematic hardening model based on a differential evolution optimization method. To this goal, several tension-compression (TC) tests were conducted to observe the Bauchinger’s effects and kinematic hardening behaviors of two aluminum alloy sheets: AA6022-T6 and AA7075-T76. A Python code is developed to apply the proposed method in identifying parameters of the kinematic hardening model. The calibrated material models were implemented in Abaqus software to simulate V-bending and U-bending tests for the investigated materials. The predictions for springback amount match well with the experimental measurements, which verifies the effectiveness of the presented identificationstrategy.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.","PeriodicalId":250655,"journal":{"name":"J. Adv. Eng. Comput.","volume":"515 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131531660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-30DOI: 10.55579/jaec.202263.381
K. Takizawa, Y. Bazilevs, T. Tezduyar, M. Hsu, Takuya Terahara
Isogeometric analysis (IGA) brought superior accuracy to computations in both fluid and solid mechanics. The increased accuracy has been in representing both the problem geometry and the variables computed. Beyond using IGA basis functions in space, with IGA basis functions in time in a space–time (ST) context, we can have increased accuracy also in representing the motion of solid surfaces. Around the core methods such as the residual-based variational multiscale (VMS), ST-VMS and arbitrary Lagrangian–Eulerian VMS methods, with complex-geometry IGA mesh generation methods and immersogeometric analysis, and with special methods targeting specific classes of computations, the IGA has been very effective in computational cardiovascular medicine. We provide an overview of these IGA-based computational cardiovascular-medicine methods and present examples of the computations performed.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.
{"title":"Computational Cardiovascular Medicine With Isogeometric Analysis","authors":"K. Takizawa, Y. Bazilevs, T. Tezduyar, M. Hsu, Takuya Terahara","doi":"10.55579/jaec.202263.381","DOIUrl":"https://doi.org/10.55579/jaec.202263.381","url":null,"abstract":"Isogeometric analysis (IGA) brought superior accuracy to computations in both fluid and solid mechanics. The increased accuracy has been in representing both the problem geometry and the variables computed. Beyond using IGA basis functions in space, with IGA basis functions in time in a space–time (ST) context, we can have increased accuracy also in representing the motion of solid surfaces. Around the core methods such as the residual-based variational multiscale (VMS), ST-VMS and arbitrary Lagrangian–Eulerian VMS methods, with complex-geometry IGA mesh generation methods and immersogeometric analysis, and with special methods targeting specific classes of computations, the IGA has been very effective in computational cardiovascular medicine. We provide an overview of these IGA-based computational cardiovascular-medicine methods and present examples of the computations performed.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.","PeriodicalId":250655,"journal":{"name":"J. Adv. Eng. Comput.","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125644161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-30DOI: 10.55579/jaec.202263.369
M. Sukkar, D. Kumar, Jigneshsinh Sindha
There are sub-classes of pedestrians that can be defined and it is important to distinguish between them for the detection in autonomous vehicle applications, such as elderly, and children, to reduce the risk of collision. It is necessary to talk about effective pedestrian tracking besides detection so that object remains accurately monitored, here the effective pre-trained algorithms come to achieve this goal in real-time. In this paper, we make a comparison between the detection and tracking algorithms, we applied the transfer learning technique to train the detection model on new sub-classes, after making Images augmentation in previous work, we got better results in detection, reached 0.81 mAP in real-time by using Yolov5 model, with a good tracking performance by the tracking algorithm dependent on detection Deep-SORT.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.
{"title":"Improve Detection and Tracking of Pedestrian Subclasses by Pre-Trained Models","authors":"M. Sukkar, D. Kumar, Jigneshsinh Sindha","doi":"10.55579/jaec.202263.369","DOIUrl":"https://doi.org/10.55579/jaec.202263.369","url":null,"abstract":"There are sub-classes of pedestrians that can be defined and it is important to distinguish between them for the detection in autonomous vehicle applications, such as elderly, and children, to reduce the risk of collision. It is necessary to talk about effective pedestrian tracking besides detection so that object remains accurately monitored, here the effective pre-trained algorithms come to achieve this goal in real-time. In this paper, we make a comparison between the detection and tracking algorithms, we applied the transfer learning technique to train the detection model on new sub-classes, after making Images augmentation in previous work, we got better results in detection, reached 0.81 mAP in real-time by using Yolov5 model, with a good tracking performance by the tracking algorithm dependent on detection Deep-SORT.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.","PeriodicalId":250655,"journal":{"name":"J. Adv. Eng. Comput.","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124898664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：